#!/bin/bash

# findsn - find duplicate names in the specified tree(s).
# Copyright © 2000-2009 by Pádraig Brady <P@draigBrady.com>.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU General Public License for more details,
# which is available at www.gnu.org


# Notes:
#
# It defaults to looking through the PATH as this
# is usually what you want to check. In this mode
# it has the same functionality as chkdupexe
# (which also has the functionality of checking
# for dangling links that findbl does).
#	If you specify paths on the command line,
# then it searches there for duplicate names.
#
# Note unlike the other utils, to look in the current
# directory you must explicitly specify it (using . for
# e.g.)
#
# Note it's not obvious but you don't have to specify
# LC_COLLATE=C anywhere in this script.
#
# Todo: give option to include directory names & or symbolic links
# Todo: give option to exclude links that point to same file

script_dir=$(dirname "$0")              #directory of this script
script_dir=$(readlink -f "$script_dir") #Make sure absolute path

. "$script_dir"/supprt/fslver

Usage() {
    ProgName=$(basename "$0")
    echo "find (files) with duplicate or conflicting names.
Usage: $ProgName [-A -c -C] [[-r] [-f] paths(s) ...]

If no arguments are supplied the \$PATH is searched for any redundant
or conflicting files.

-A reports all aliases (soft and hard links) to files.
If no path(s) specified then the \$PATH is searched.

If only path(s) specified then they are checked for duplicate named
files. You can qualify this with -C to ignore case in this search.
Qualifying with -c is more restictive as only files (or directories)
in the same directory whose names differ only in case are reported.
I.E. -c will flag files & directories that will conflict if transfered
to a case insensitive file system. Note if -c or -C specified and
no path(s) specifed the current directory is assumed."

    exit
}

mode="matchFilenames"
uniqsep=prepend

topipe=no
if [ -p /proc/self/fd/1 ]; then
    topipe=yes
fi

if [ $# -eq "0" ]; then #Nothing on cmdline means search $PATH
    mode="path"
    eval set -- $(. "$script_dir"/supprt/getffp)
    FPF="%p"
elif [ $# -eq "1" ] && [ "$1" = "-A" ]; then
    mode="aliases"
    eval set -- $(. "$script_dir"/supprt/getffp)
    FPF="%p"
else
    for arg; do
        case "$arg" in
        -h|--help|-help)
            Usage ;;
        -v|--version)
            Version ;;
        -C)
            uniq_ignore_case="-i"
            sort_ignore_case="-f" ;;
        -c)
            mode="casePortability" ;;
        -A)
            mode="aliases" ;;
        *)
            argsToPassOn="$argsToPassOn $(shell_quote "$arg")" ;;
        esac
    done

    if [ $topipe = yes ]; then
        . "$script_dir"/supprt/getfpf -f "$argsToPassOn"
    else
        . "$script_dir"/supprt/getfpf "$argsToPassOn"
    fi
fi

check_uniq

translate()
{
   case "$1" in
   safe) #change problem chars
      tr ' \t\n\1\0' '\2\3\4 \n' ;;
   safe2pipe)
      tr '\2\3\4\n' ' \t\n\0' ;;
   safe2human)
      tr '\2\3\4' ' \t\n' ;;
   esac
}

auto_ignore_paths()
{
   echo "-true"
   #ignore common $PATH dependent programs
   echo "
   /usr/bin/ccache
   /usr/bin/consolehelper
   /usr/sbin/lvm
   /sbin/lvm.static
   " | sed '/ *#/d; /^ *$/d' | #remove comments and blank lines
   while read path; do
       inode=$(find "$path" -printf "%i" 2>/dev/null)
       [ "$inode" ] && echo -n " -and ! -inum $inode"
   done
}

case "$mode" in

casePortability)
   find "$@" \( -type d -o -type f \) -printf "%f\1$FPF\1%h\0" |
   sort -zu | #merge files (indirectly) specified multiple times
   translate safe |
   sort -b -k3,3 -k1,1f | #group paths (case sens), then names (case insens)
   uniq -2 -D |
   uniq -i --all-repeated=$uniqsep |
   cut -f2 -d' ' ;;
matchFilenames)
   find "$@" -type f -printf "$FPF\1%f\0" |
   sort -zu | #merge files (indirectly) specified multiple times
   translate safe |
   sort $sort_ignore_case -k2,2 |
   uniq --all-repeated=$uniqsep -1 $uniq_ignore_case ;;
path)

   find "$@" \( -type f -o -type l \) -follow \( $(auto_ignore_paths) \) \
        -printf "$FPF\1%i\1%f\0" |
   sort -zu | #merge files (indirectly) specified multiple times
   translate safe |
   sort -k3,3 -k2,2n |
   uniq -D -2 |
   uniq -1 |
   uniq --all-repeated=$uniqsep -2 ;;
aliases)
   find "$@" \( -type f -o -type l \) -follow -printf "$FPF\1%i\0" |
   sort -zu | #merge files (indirectly) specified multiple times
   translate safe |
   sort -k2,2n |
   uniq --all-repeated=$uniqsep -1 ;;
esac |
   cut -f1 -d' ' |
   if [ $topipe = yes ]; then
      translate safe2pipe
   else
      #one can change this block to "translate safe2human" for grouped output
      #Alternatively you can pipe output to "tr '\0' '\n'"
      sed '/^ *$/d' |
      translate safe2pipe |
      xargs -r0 ls -lbUd --color=auto --
   fi